Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks281 from public data
- Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning582
This paper proposes a novel method called reasoning on graphs (RoG) that synergizes LLMs with KGs to enable faithful and interpretable reasoning and presents a planning-retrieval-reasoning framework, where RoG first generates relation paths grounded by KGs as faithful plans.
- XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages570
This work presents XL-Sum, a comprehensive and diverse dataset comprising 1 million professionally annotated article-summary pairs from BBC, extracted using a set of carefully designed heuristics, and is the largest abstractive summarization dataset in terms of the number of samples collected from a single source and thenumber of languages covered.
- VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks231
VLABench is an open-source benchmark for evaluating universal LCM task learning and provides high-quality training data collected via an automated framework incorporating heuristic skills and prior information to support the downstream finetuning.
- Multivariate Time Series Forecasting With Dynamic Graph Neural ODEs206
A continuous model to forecast multivariate time series forecasting is proposed, designed and solved to complement missing graph topologies and unify both spatial and temporal message passing, allowing deeper graph propagation and fine-grained temporal information aggregation to characterize stable and precise latent spatial-temporal dynamics.
- ANEMONE200
A novel graph anomaly detection framework, namely ANEMONE, to simultaneously identify the anomalies in multiple graph scales and employs a statistical anomaly estimator to evaluate the abnormality of each node according to the degree of agreement from multiple perspectives.
- Continual Learning for Large Language Models: A Survey198
This paper surveys recent works on continual learning for LLMs and catalogs continue learning techniques in a novel multi-staged categorization scheme, involving continual pretraining, instruction tuning, and alignment.
- Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning194
A novel self-supervised approach to learn node representations by enhancing Siamese self-distillation with multi-scale contrastive learning that not only achieves new state-of-the-art results but also surpasses some semi- supervised counterparts by large margins.
- Measuring design complexity of semantic web ontologies134
This paper proposes a suite of ontology metrics, at both the ontology-level and class-level, to measure the design complexity of ontologies, and points out possible applications of the proposed metrics to ontology quality control.
- Verifying feature models using OWL133
A general OWL debugger has been developed to tackle the disadvantage of lacking debugging aids for the current OWL reasoner and to complement the verification approach to modeling and verifying feature diagrams using Semantic Web OWL ontologies.
- Neural Temporal Walks: Motif-Aware Representation Learning on Continuous-Time Dynamic Graphs131
A new approach, Neural Temporal Walks ( NeurTWs), for representation learning on continuous-time dynamic graphs by considering not only time constraints but also structural and tree traversal properties, demonstrates overwhelming superiority under both transductive and inductive settings on six real-world datasets.
- Two decades of Web application testing—A survey of recent advances90
A broad survey of recent Web testing advances is presented and it is discussed their goals, targets, techniques employed, inputs/outputs and stopping criteria.
- Curriculum-Meta Learning for Order-Robust Continual Relation Extraction89
A novel curriculum-meta learning method is proposed to quickly adapt model parameters to a new task and to reduce interference of previously seen tasks on the current task to tackle catastrophic forgetting and order-sensitivity in continual relation extraction.
- Difficulty-Controllable Multi-hop Question Generation from Knowledge Graphs86
This work presents an end-to-end neural network-based method for automatic generation of complex multi-hop questions over knowledge graphs, and incorporates difficulty estimation based on named entity popularity, and makes use of this estimation to generate difficulty-controllable questions.
- An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models76
A novel VQA dataset is constructed, Spatial-MM, to comprehensively study large Multimodal Models’ spatial understanding and reasoning capabilities and reveals that LMMs are much stronger at basic object detection than complex spatial reasoning.
- Predicting Reasoning Performance Using Ontology Metrics74
A systematic study to tackle hardness of reasoning about individual ontologies using machine learning techniques, covering over 350 real-world ontologies and four state-of-the-art, widely-used OWL 2 reasoners and identifying a number of metrics that can be used to effectively predict reasoning performance.
- A semantic web approach to feature modeling and verification74
A Semantic Web environment for modeling and verifying feature diagrams using ontologies using OWL DL (a decidable dialect of OWL) to precisely capture the relationships among features in feature diagrams and configurations.
- Structured Two-Stream Attention Network for Video Question Answering73
This paper proposes a Structured Two-stream Attention network, namely STA, to answer a free-form or open-ended natural language question about the content of a given video to infer rich longrange temporal structures in videos using the authors' structured segment component and encode text features.
- Multimodal feature-wise co-attention method for visual question answering66
By introducing MulFA modules, this paper constructs an effective union feature-wise and spatial co-attention network (UFSCAN) model for VQA, and evaluation on two large-scale V QA datasets shows that UFSCAN achieves performance competitive with state-of-the-art models.
- Generating question titles for Stack Overflow from mined code snippets66
An approach to assist developers in writing high-quality questions by automatically generating question titles for a code snippet using a deep sequence-to-sequence learning approach that significantly outperforms several state-of-the-art baselines in both automatic and human evaluation.
- MMGRec: Multimodal Generative Recommendation with Transformer Model63
A relation-aware self-attention mechanism is devised for the Transformer to handle non-sequential interaction sequences, which explores the element pairwise relation to replace absolute positional encoding.
- CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairs62
A multistage data sampling algorithm is proposed to effectively train a cross-lingual summarization model capable of summarizing an article in any target language and LaSE, an embedding-based metric for automatically evaluating model-generated summaries is introduced.
- Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph Completion60
A normalizing flow-based neural process for few-shot knowledge graph completion (NP-FKGC), which unify normalizing flows and neural processes to model a complex distribution of KG completion functions and introduces an attentive relation path-based graph neural network to capture path information in KGs.
- Combining cross-modal knowledge transfer and semi-supervised learning for speech emotion recognition53
This work proposes a new architecture that combines cross-modal knowledge transfer from visual to audio modality into the authors' semi-supervised learning method with consistency regularization, and proposes two fusion algorithms, i.e. weighted fusion and consistent & random.
- Automating Reading Comprehension by Generating Question and Answer Pairs50
A novel two-stage process to generate question-answer pairs from the text using sequence to sequence models and global attention and answer encoding for generating the question most relevant to the answer is presented.
- A framework for automatic question generation from text using deep reinforcement learning.48
This paper presents a novel deep reinforcement learning based framework for automatic question generation that significantly outperforms state-of-the-art systems on the widely-used SQuAD benchmark in both automatic and human evaluation.
- 47
- 46
- Putting the Horse before the Cart: A Generator-Evaluator Framework for Question Generation from Text46
This work adopts a holistic and novel generator-evaluator framework that directly optimizes objectives that reward semantics and structure in automatic question generation and proposes two novel QG-specific reward functions for text conformity and answer conformity of the generated question.
- Exploiting Scene Graphs for Human-Object Interaction Detection45
Empirical evaluation shows that the proposed SG2HOI method outperforms the state-of-the-art methods on two benchmark HOI datasets: V-COCO and HICO-DET.
- 44
- An ontology-centric architecture for extensible scientific data management systems44
This paper presents an ontology-centric architecture for data management systems that is extensible and domain independent, and applies it to the challenge of managing phenomics data.
- Learning from the Scene and Borrowing from the Rich: Tackling the Long Tail in Scene Graph Generation43
This paper tackles the issue of scene-object interaction aiming at learning specific knowledge from a scene via an additive attention mechanism and long-tail knowledge transfer which tries to transfer the rich knowledge learned from the head into the tail.
- Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection42
This work proposes a novel knowledge-based few-shot event detection method which uses a definition-based encoder to introduce external event knowledge as the knowledge prior of event types, and introduces an adaptive knowledge-enhanced Bayesian meta-learning method to dynamically adjust theknowledge prior ofevent types.
- Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning42
A meta-reinforcement learning approach to program induction in CQA to tackle the potential distributional bias in questions and achieves state-of-the-art performance while using only five trial trajectories for the top-5 retrieved questions in each support set and meta-training on tasks constructed from only 1% of the training set.
- MonaGO: a novel gene ontology enrichment analysis visualisation system41
MonaGO is a novel web-based visualisation system that provides an intuitive, interactive and responsive interface for performing GO enrichment analysis and visualising the results, and will facilitate the interpretation of GO analysis and will assist the biologists into the representation of the results.
- Boosting house price predictions using geo-spatial network embedding41
A novel method is presented, the geo-spatial network embedding (GSNE), that learns the embeddings of houses and various types of points of interest in the form of multipartite networks, where the houses and the POIs are represented as attributed nodes and the relationships between them as edges.
- Knowledge-enriched, Type-constrained and Grammar-guided Question Generation over Knowledge Bases37
This work proposes an innovative knowledge-enriched, type-constrained and grammar-guided KBQG model, named KTG, which outperforms existing methods by a significant margin on two widely-used benchmark datasets SimpleQuestion and PathQuestion.
- BioVis Explorer: A visual guide for biological data visualization techniques37
An interactive web-based visualization tool, the BioVis Explorer, which allows the exploration of published visualization methods in interactive and intuitive ways, including faceted browsing and associations with related methods.
- A combined approach to checking web ontologies35
This work proposes to use the software engineering techniques and tools, i.e., Z/EVES and Alloy Analyzer, to complement the ontology tools for checking Semantic Web documents and has successfully applied this approach to checking a set of military plan ontologies.
- Toward Graph Self-Supervised Learning With Contrastive Adjusted Zooming34
This work introduces a novel self-supervised GRL algorithm via graph contrastive adjusted zooming, namely, G-Zoom, to learn node representations by leveraging the proposedadjusted zooming scheme, and demonstrates that this proposed model outperforms the state-of-the-art methods consistently.
- 34
- Hier-SLAM: Scaling-Up Semantics in SLAM with a Hierarchically Categorical Gaussian Splatting32
Hier-SLAM is proposed, a semantic 3D Gaussian Splatting SLAM method featuring a novel hierarchical categorical representation that encodes semantic information in a compact form into 3D Gaussian Splatting, leveraging the capabilities of large language models (LLMs).
- 30
- 30
- Less is more: Data-efficient complex question answering over knowledge bases30
The Neural-Symbolic Complex Question Answering (NS-CQA) model is proposed, a data-efficient reinforcement learning framework for complex question answering by using only a modest number of training samples and outperforms the state-of-the-art models on two datasets.
- How Long Will It Take? Accurate Prediction of Ontology Reasoning Performance29
This paper develops predictive models to estimate actual classification time using regression techniques, with ontology metrics as features, and demonstrates how they can be used to efficiently and accurately identify performance hotspots in a large and complex ontology, an otherwise very time-consuming and resource-intensive task.
- 28
- VersiCode: Towards Version-controllable Code Generation28
An extensive evaluation on VersiCode reveals that version-controllable code generation is indeed a significant challenge, even for GPT-4o and other strong frontier models, and proposes two novel tasks aimed at bridging this gap: version-specific code completion (VSCC) and version-aware code migration (VACM).
- 28
- 25
- Toward a Unified Transformer-Based Framework for Scene Graph Generation and Human-Object Interaction Detection24
This work introduces SG2HOI+, a unified one-step model based on the Transformer architecture that employs two interactive hierarchical Transformers to seamlessly unify the tasks of SGG and HOI detection and achieves competitive performance when compared to state-of-the-art HOI methods.
- 23
- Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition23
An Unsupervised Cross-Domain Visual Emotion Recognition (UCDVER) task, which aims to generalize visual emotion recognition from the source domain to the low-resource target domain in an unsupervised manner and surpasses SOTA models in both perceptibility and generalization.
- Factors of Collective Intelligence: How Smart Are Agent Collectives?23
This paper develops the idea of collective intelligence by giving some insight into a range of factors hindering and influencing the effectiveness of interactive cognitive systems, and empirically shows that collective intelligence is a function of them all simultaneously.
- Towards Effective Data-Free Knowledge Distillation via Diverse Diffusion Augmentation22
This paper revise the paradigm of common data synthesis in DFKD to a composite process through leveraging diffusion models subsequent to data synthesis for self-supervised augmentation, which generates a spectrum of data samples with similar distributions while retaining controlled variations.
- KGVQL: A knowledge graph visual query language with bidirectional transformations22
This paper presents a knowledge graph interactive visual query language, KGVQL, to improve the efficiency of end-users’ understanding and querying of knowledge graphs, and empirically evaluates the effectiveness of a visual query system based on KGVQ against a number of textual and visual query environments over a large knowledge graph, DBpedia.
- Simple or Complex? Complexity-controllable Question Generation with Soft Templates and Deep Mixture of Experts Model21
This paper proposes an end-to-end neural complexity-controllable question generation model, which incorporates a mixture of experts as the selector of soft templates to improve the accuracy of complexity control and the quality of generated questions.
- MedGraph: Structural and Temporal Representation Learning of Electronic Medical Records21
A supervised EMR embedding method that captures two types of information: the visit-code associations in an attributed bipartite graph, and the temporal sequencing of visits through a point process that outperforms state-of-the-art E MR embedding methods in several medical risk prediction tasks.
- Pytester: Deep reinforcement learning for text-to-testcase generation20
PyTester is introduced, a Text-to-Testcase generation approach that can automatically generate syntactically correct, executable, complete, and effective test cases while being aligned with a given natural language requirement and suggests that future research could consider improving small over large LMs for better resource efficiency.
- Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting19
A theoretical framework is established that unravels the expressive power of spectral-temporal GNNs and proposes a simple instantiation named Temporal Graph Gegenbauer Convolution (TGGC), which significantly outperforms most existing models with only linear components and shows better model efficiency.
- Weighted gene coexpression network analysis identifies specific transcriptional modules and hub genes related to intramuscular fat traits in chicken breast muscle19
A weighted gene coexpression network analysis between IMF traits and transcriptome profile in breast muscle in the Chinese domestic Gushi chicken breed provides novel insights into the molecular regulatory mechanisms for IMF‐related traits in chicken and may also help to uncover the formation mechanism for excellent meat quality traits in local breeds of Chinese chicken.
- One Network for Multi-Domains: Domain Adaptive Hashing with Intersectant Generative Adversarial Networks19
An end-to-end domain adaptive learning framework that simultaneously and precisely generates discriminative hash codes and classifies target domain images that is superior to the other state-of-the-art methods on the tasks of object recognition and image retrieval.
- Understanding and improving ontology reasoning efficiency through learning and ranking19
A comprehensive evaluation on a large and carefully curated ontology corpus shows that R 2 O 2 * outperforms all six component reasoners as well as AutoFolio, a robust and strong algorithm selection system.
- CATERPILLAR: Coarse Grain Reconfigurable Architecture for accelerating the training of Deep Neural Networks19
An algorithm/architecture space exploration of efficient accelerators to achieve better network convergence rates and higher energy efficiency for training DNNs and demonstrates that an architecture with hierarchical support for collective communication semantics provides flexibility in training various networks performing both stochastic and batched gradient descent based techniques.
- NEUSIS: A Compositional Neuro-Symbolic Framework for Autonomous Perception, Reasoning, and Planning in Complex UAV Search Missions18
Experimental results from simulated urban search missions using AirSim and Unreal Engine show that NEUSIS outperforms state-of-the-art baselines for both perception and planning, making it a promising solution for autonomous UAV systems in search missions.
- Decompose, Enrich, and Extract! Schema-aware Event Extraction using LLMs.18
This work introduces a new method to address hallucination by decomposing the task into Event Detection and Event Argument Extraction, and integrates dynamic schema-aware augmented retrieval examples into prompts tailored for each specific inquiry, thereby extending and adapting advanced prompting techniques such as Retrieval-Augmented Generation.
- Hierarchical machine learning models can identify stimuli of climate change misinformation on social media18
An analysis of five million climate-themed social-media posts identified four distinct spikes in climate change misinformation, using a two-step hierarchical model in machine learning.
- Code2Que: a tool for improving question titles from mined code snippets in stack overflow18
A new web-based tool, Code2Que, which can help developers in writing higher quality questions for a given code snippet through a deep sequence-to-sequence approach, enhanced with an attention mechanism, a copy mechanism and a coverage mechanism.
- SNEQ: Semi-Supervised Attributed Network Embedding with Attention-Based Quantisation18
Evaluation on four real-world networks of diverse characteristics shows that SNEQ outperforms a number of state-of-the-art embedding methods in link prediction, node classification and node recommendation and the quantised embedding shows a great advantage in terms of storage and time compared with continuous embeddings as well as hashing methods.
- Proceedings of the 10th annual joint conference on Digital libraries18
The theme of JCDL 2010, "Digital Libraries -- 10 Years Past, 10 Years Forward, A 2020 Vision", addresses both the historical legacy of this conference and the challenges that lie ahead as the technical, cultural, political, and social contexts in which the field is situated continue to change.
- Semantic Web Languages – Towards an Institutional Perspective18
It is shown that RDF framework together with the RDF serializations of SW languages form an indexed institution, which allows the use of Grothendieck institutions to combine Web ontologies described in various languages.
- Deep Evidential Hashing for Trustworthy Cross-Modal Retrieval17
This paper proposes a novel method called Deep Evidential Cross-modal Hashing (DECH), which equips hashing models with the ability to quantify the reliability level of the association between a query sample and each corresponding retrieved sample, bringing a new dimension of reliability to the cross-modal retrieval process.
- 17
- 17
- RobustiQ: A Robust ANN Search Method for Billion-scale Similarity Search on GPUs17
This paper introduces a new GPU-based ANN search method, Robust Quantization (RobustiQ), that addresses the robustness limitations of existing GPU- based methods in a holistic way and designs a novel hierarchical indexing structure using vector and bilayer line quantization.
- Cinemo: Consistent and Controllable Image Animation with Motion Diffusion Models16
This paper introduces Cinemo, a novel image animation approach towards achieving better motion controllability, as well as stronger temporal consistency and smoothness, and proposes three effective strategies at the training and inference stages of Cinemo to accomplish this goal.
- Modelling Political Coalition Negotiations Using LLM-based Agents16
A multilingual dataset, POLCA, comprising manifestos of European political parties and coalition agreements over a number of elections in these countries is introduced and a hierarchical Markov decision process designed to simulate the process of coalition negotiation between political parties and predict the outcomes is proposed.
- 16
- Vector and line quantization for billion-scale similarity search on GPUs16
A novel hierarchical inverted index structure generated by vector and line quantization methods is proposed that significantly outperforms the state-of-the-art GPU- and CPU-based systems in terms of both accuracy and search speed.
- PODD: An Ontology-Driven Data Repository for Collaborative Phenomics Research16
This paper describes the effort in designing and developing an ontology-driven, open, extensible data repository to support collaborative phenomics research in Australia.
- 15
- From Planning Stage Towards FAIR Data: A Practical Metadatasheet For Biomedical Scientists15
This study developed Metadatasheet, a metadata standard based on interviews with members of two biomedical consortia and systematic screening of data repositories that aligns with the data-lifecycle allowing synchronous metadata recording within Microsoft Excel, a widespread data recording software.
- Semisupervised Network Embedding With Differentiable Deep Quantization15
d-SNEQ is developed, a differentiable DNN-based quantization method for network embedding that incorporates a rank loss to equip the learned quantization codes with rich high-order information and is able to substantially compress the size of trained embeddings, thus reducing storage footprint and accelerating retrieval speed.
- Robust Attribute and Structure Preserving Graph Embedding15
RASE is a novel graph representation learning model which effectively preserves both graph structure and node attributes through a unified loss function, and is robust to both structure and attribute noise.
- 14
- A photosynthetic rate prediction model using improved RBF neural network14
A method based on Radial basis function (RBF) optimized by Quantum genetic algorithm (QGA) to establish photosynthetic rate prediction model that has the highest accuracy compared with other algorithms is proposed.
- 14
- Enhancing Semantic Web Services with Inheritance14
OWL-S is extended with the ability to define and maintain inheritance relationships between services with the definition of an additional "inheritance profile" and two types of IRs are allowed to grant service developers the choice to respect the "contract" between services or not.
- INFORMATION TECHNOLOGY ADDRESSES TRANSPARENCY: THE POTENTIAL EFFECTS OF XBRL ON FINANCIAL DISCLOSURE14
Financial statements in XBRL format allow financial report users to directly search for relevant information regardless of the location of the information and to easily compare related information between different companies.
- SPADE: Spatial-Aware Denoising Network for Open-Vocabulary Panoptic Scene Graph Generation with Long- and Local-Range Context Reasoning13
SPADE (SPatial-Aware Denoising-nEtwork) framework-a novel approach for open-vocabulary PSG that outperforms state-of-the-art methods in both closed- and open-set scenarios, particularly for spatial relationship prediction.
- 13
- Towards Open-vocabulary HOI Detection with Calibrated Vision-language Models and Locality-aware Queries13
This work proposes a two-step framework named, CaM-LQ, Calibrating visual-language Models, for open-vocabulary HOI detection with Locality-aware Queries, and injects fine-grained HOI supervision from the calibrated CLIP into the HOI decoder to achieve the goal of predicting novel interactions.
- Predicting Reasoner Performance on ABox Intensive OWL 2 EL Ontologies13
The authors introduce the notion of ABox intensity in the context of predicting reasoner performance to improve the representativeness of ontology metrics, and they develop new metrics that focus on ABox features of OWL 2 EL ontologies.
- Predicting Energy Consumption of Ontology Reasoning over Mobile Devices13
An energy consumption prediction mechanism for ontology Reasoning on mobile devices is introduced that allows an analysis of the feasibility of performing an ontology reasoning on a mobile device with respect to energy consumption and helps to improve further developments in semantic reasoning in general.
- Using Semantic Web Technologies to Build a Community-Driven Knowledge Curation Platform for the Skeletal Dysplasia Domain13
The paper presents the community requirements driving the design of the platform, the underlying implementation details and the results of a preliminary usability study, and discusses the limitations of some of its embedded Semantic Web components.
- A Z Approach in Validating ORA-SS Data Models13
This paper demonstrates an approach to formally validate the ORA-SS data models in order to enhance the correctness of semistructured data design.
- A Survey on Web Application Testing: Over a Decade of Evolution12
The main steps involved in WAT, including test-case generation and execution, and evaluation and assessment are examined, including test-case generation and execution, and evaluation and assessment.
- Augmented CARDS: A machine learning approach to identifying triggers of climate change misinformation on Twitter12
This study develops a two-step hierarchical model, the Augmented CARDS model, specifically designed for detecting contrarian climate claims on Twitter, and applies it to five million climate-themed tweets over a six-month period in 2022.
- A Multi-Modal Deep Learning Based Approach for House Price Prediction12
A multi-modal deep learning approach that leverages different types of data to learn more accurate representation of the house by comprehensively incorporating attributes, such as features, textual descriptions, geo-spatial neighborhood, and house images, typically showcased in real estate listings in a house price prediction system.
- 12
- lp Norm Smooth Inversion of Magnetic Anomaly Based on Improved Adaptive Differential Evolution12
An improved adaptive differential evolution is proposed to solve the lp norm magnetic inversion of 2D data, in which the perturbation direction in the mutation strategy is smoothed by using the moving average technique.
- 12
- An Information-Theoretic Predictive Model for the Accuracy of AI Agents Adapted from Psychometrics12
A new model to quantitatively estimate the accuracy of artificial agents over cognitive tasks of approximable complexities is proposed, derived by introducing notions from algorithmic information theory into a well-known measurement paradigm called Item Response Theory (IRT).
- KC-GEE: knowledge-based conditioning for generative event extraction11
This work proposes a generative event extraction model, KC-GEE, that achieves particularly strong results in the challenging document-level extraction task and in the zero-shot learning setting, outperforming state-of-the-art models by up to 5.4 absolute F1 points.
- Complex Reading Comprehension Through Question Decomposition11
This work proposes a novel learning approach that helps language models better understand difficult multi-hop questions and perform "complex, compositional"reasoning in a sequence-to-sequence manner.
- 11
- Observation, Communication and Intelligence in Agent-Based Systems11
Results show that the effectiveness of multiagent systems with low observation/perception abilities can be significantly improved by using high communication entropies within the agents in the system.
- The Ubiquitous Semantic Web11
The authors argue for values provided by the ubiquitous Semantic Web using a mobile service discovery scenario and provide a brief overview of state-of-the-art research in this emerging area.
- A Rigorous Characterization of Classification Performance - A Tale of Four Reasoners.11
A comprehensive comparative study to analyze classification performance of four widely-used reasoners, FaCT++, HermiT, Pellet and TrOWL, using a dataset of over 300 real-world ontologies to provide additional insights into the hardness of individual ontologies.
- XML-Based Static Type Checking and Dynamic Visualization for TCOZ11
The development of a type checker for detecting static semantic errors of the TCOZ specification is demonstrated, and a transformation tool to automatically project T COZ models into UML statechart diagrams for visualising the dynamic system behaviour is illustrated.
- MSBiLSTM-Attention: EEG Emotion Recognition Model Based on Spatiotemporal Feature Fusion10
A novel deep learning technique that integrates multi-scale convolution and bidirectional long short-term memory networks with an attention mechanism for automatic EEG feature extraction and classification, and suggests that the MSBiLSTM-Attention model is a powerful approach for emotion recognition.
- Informative Scene Graph Generation via Debiasing10
DB-SGG is proposed, an effective framework based on debiasing but not the conventional distribution fitting that can be easily applied to SGG models and outperforms Transformer by 136.3% on mR@20 at three SGG sub-tasks on the SGG-VG dataset.
- 10
- 10
- 10
- ParaQG: A System for Generating Questions and Answers from Paragraphs10
ParaQG, a Web-based system for generating questions from sentences and paragraphs based on sequence-to-sequence techniques, is demonstrated and incorporates a number of novel functionalities to make the question generation process user-friendly.
- Measuring Universal Intelligence in Agent-Based Systems Using the Anytime Intelligence Test10
A universal metric is proposed and used to empirically measure intelligence for several different agent decision controllers and reflects the different settings over which cooperative multiagent systems can be significantly more intelligent per agent than others.
- 10
- Multi-Cultural Norm Base: Frame-based Norm Discovery in Multi-Cultural Settings9
This paper presents a robust automatic norm discovery pipeline, which utilizes the cultural knowledge of GPT-3.5 Turbo (ChatGPT) along with several social factors, and shows remarkable results on various downstream tasks, outperforming models fine-tuned on other datasets significantly.
- Hypergraph Node Representation Learning with One-Stage Message Passing9
HGraphormer injects the hypergraph structure information into Transformers (local information) into Transformers (global information) by combining the attention matrix and hypergraph Laplacian, a Transformer-based framework for hypergraph node representation learning.
- GraSS: An Efficient Method for RDF Subgraph Matching9
This paper presents a subgraph matching query engine based on the FFD-index which is an indexing mechanism encoding a star subgraph into a bit string, and shows that this approach outperforms RDF-3X and gStore on solving sub graph matching.
- 8
- Gaussian Embedding of Large-Scale Attributed Graphs8
This work proposes GLACE, a novel, scalable graph embedding method that preserves both graph structure and node attributes effectively and efficiently in an end-to-end manner and significantly outperforms state-of-the-art embedding methods on multiple graph analysis tasks.
- Scalable computational geometry in MapReduce8
CG_Hadoop is introduced; a suite of scalable and efficient MapReduce algorithms for various fundamental computational geometry operations, namely polygon union, Voronoi diagram, skyline, convex hull, farthest pair, and closest pair, which present a set of key components for other geometric algorithms.
- 8
- Enriching An Academic knowledge base using Linked Open Data8
This paper identifies mappings between a subset of its predicates and those in DBpedia and other linked datasets and shows how these along with semantic web standards and tools enable it to populate the academic ontology.
- Integrating software engineering data using semantic web technologies8
This paper describes how Semantic Web techniques are applied to integrate object-oriented software engineering data from different sources and shows how the integrated data can help us answer complex queries about large-scale software projects through a case study on the Eclipse system.
- Institution Morphisms for Relating OWL and Z8
The advantage that the logics underlying OWL and Z can be represented as institutions is taken and it is shown that the institution comorphism provides a formal semantic foundation for the transformation from OWL to Z.
- 8
- Towards Lifelong Scene Graph Generation with Knowledge-ware In-context Prompt Learning7
This work introduces a novel and pragmatic framework for scene graph generation, namely Lifelong Scene Graph Generation (LSGG), where tasks, such as predicates, unfold in a streaming fashion and imbues the model with the capability to predict relationships and continuously acquire novel knowledge without succumbing to catastrophic forgetting.
- 7
- 7
- 7
- OntoPlot: A Novel Visualisation for Non-hierarchical Associations in Large Ontologies7
OntoPlot is presented, a novel visualisation specifically designed to facilitate the exploration of all concept associations whilst still showing an ontology's large hierarchical structure, which combines icicle plots, visual compression techniques and interactivity, improving space-efficiency and reducing visual structural complexity.
- A survey on the use of access permission-based specifications for program verification7
A comprehensive survey of existing access permission-based verification approaches based on permission usage, analysis performed, language and/or tool supported, and properties being verified is provided.
- Footprints of fitness functions in search-based software testing7
The Mapping the Effectiveness of Test Automation (META) Framework is proposed which analyses the footprint of different fitness functions and creates a decision tree that enables the selection of the appropriate function based on software features.
- 7
- 6
- 6
- 6
- 6
- Explicit Query Interpretation and Diversification for Context-Driven Concept Search Across Ontologies6
This paper proposes a keyword-based concept search framework, which exploits the structure and semantics in ontologies, by constructing contexts for each concept, which generates the interpretations of a query and balances the relevance and diversity of search results.
- 6
- 6
- Transitioning Applications to Semantic Web Services: An Automated Formal Approach6
This paper proposes a methodology for transitioning legacy systems to Semantic Web Services by taking the advantage of rigorous mathematical methods, and allows users to migrate their applications to Semantics Web Services platform automatically or semi-automatically.
- 6
- HeGTa: Leveraging Heterogeneous Graph-enhanced Large Language Models for Few-shot Complex Table Understanding5
HeGTa, a heterogeneous graph (HG)-enhanced large language model (LLM) designed for few-shot TU tasks, aligns structural table semantics with the LLM's parametric knowledge through soft prompts and instruction tuning.
- Scalable Frame-Based Construction of Sociocultural Norm Bases for Socially Aware Dialogues5
The empirical results show the quality of the Scns derived from synthetic data is comparable to that from real dialogues annotated with gold frames, and the effectiveness of the extracted Scns in a Retrieval-Augmented Generation (RAG)-based model to reason about multiple downstream dialogue tasks.
- Few-shot Domain-Adaptative Visually-fused Event Detection from Text5
A novel domain-adaptive visually-fused event detection approach that can be trained on a few labelled image-text paired data points is presented and outperforms existing state-of-the-art models by up to 11 points.
- Toward the Automated Construction of Probabilistic Knowledge Graphs for the Maritime Domain5
The current implementation of Maritime DeepDive is reported on, together with preliminary results on extracting probabilistic events from maritime piracy incidents, and this pipeline was evaluated on a manually crafted gold standard, yielding promising results.
- 5
- BOWL: augmenting the Semantic Web with beliefs5
A new ontology language Belief-augmented OWL (BOWL) is proposed by integrating OWL DL and BAF to incorporate the notion of confidence and the abstract syntax and semantics of BOWL are defined by extending those of OWL.
- Capturing Researcher Expertise through MeSH Classification5
A novel framework for capturing and matching research expertise based on knowledge encoded in MeSH is presented and a novel and effective hybrid MeSH classification algorithm is designed by combining state-of-the-art methods.
- Visualization of Large Ontologies with Landmarks5
A novel hierarchical ontology visualization method for effectively visualizing an ontology’s global landmarks, local structure and individual class’ details and a visualization system that can handle large ontologies efficiently is presented.
- Visualizing and Simulating Semantic Web Services Ontologies5
This paper proposes to apply software engineering method and tools to visualize, simulate and verify OWL-S process models, using Live Sequence Charts to model services, capturing the inner workings of services, and its tool support Play-Engine is used to perform automated visualization, simulation and checking.
- Soundness proof of Z semantics of OWL using institutions5
This work uses institutions to represent their underlying logical systems and uses institution morphisms to prove the correctness of the Z semantics for OWL DL.
- 5
- Theia: Weakly Supervised Multimodal Event Extraction from Incomplete Data4
Theia is presented, an end-to-end multimodal event extraction framework that can be trained on incomplete data and leverages capabilities of pre-trained vision-language models and can be trained on incomplete data.
- 4
- Generating Faithful Text From a Knowledge Graph with Noisy Reference Text4
This paper develops a KG-to-text generation model that can generate faithful natural-language text from a given graph, in the presence of noisy reference text, and empower the decoder to control the level of hallucination in the generated text by employing a controllable text generation technique.
- Improving Numerical Reasoning Skills in the Modular Approach for Complex Question Answering on Text4
This work proposes effective techniques to improve NMNs' numerical reasoning capabilities by making the interpreter question-aware and capturing the relationship between entities and numbers.
- 4
- 4
- 4
- Optimizing link rate assignment and transmission scheduling in WMN through compatible set generation4
This work considers joint optimization of link rate assignment and transmission scheduling in order to maximize the minimal flow in a WMN and proposes an original heuristic based on simulated annealing that utilizes specific characteristics of the problem.
- The mobile semantic web4
This tutorial provides an overview of background knowledge in ontology languages, basic reasoning problems, and how they are applicable in the mobile environment, focusing on the reasoning and optimization techniques developed in the mTableaux framework.
- Knowledge Enrichment Analysis for Human Tissue- Specific Genes Uncover New Biological Insights4
The analyses results demonstrated that the functions of most gene groups are consistent with their tissue origins and three interesting new associations for HK genes and the skeletal muscle tissuegenes are found.
- Verify Feature Models using protegeowl4
This paper presents an approach to modeling and verifying feature diagrams usingSemantic Web ontologies, a widely-adopted means of precisely representing and formally verifying feature models in domain engineering.
- Efficient Temporal-aware Matryoshka Adaptation for Temporal Information Retrieval3
Temporal-aware Matryoshka Representation Learning (TMRL), an efficient method that equips retrievers with temporal-aware Matryoshka embeddings, leverages the nested structure of Matryoshka embeddings to introduce a temporal subspace, enhancing temporal encoding while preserving general semantic representations.
- SER-GAN: underwater image enhancement via spatially enhanced residual blocks and generative adversarial network3
A spatially enhanced residual block is designed, which employs the overall spatial information to enhance the semantic feature learning in the key regions and uses the residual structure to promote the reuse of features to improve the accuracy of the color representation.
- A Unified Hyperparameter Optimization Pipeline for Transformer-Based Time Series Forecasting Models3
This work presents a unified pipeline for HPO in transformer-based TSF and conducts extensive experiments on several state-of-the-art (SOTA) transformer-based TSF models to provide valuable guidance to both industry practitioners and academic researchers in efficiently identifying optimal hyperparameters suited to their specific domain applications.
- 3
- Towards Trustworthy and Explainable-by-Design Large Language Models for Automated Teacher Assessment3
This work proposes an explainable-by-design framework that couples Dual-Lens Hierarchical Attention with a Trust-Gated Inference module that combines Monte-Carlo-dropout calibration and adversarial debiasing, and establishes a reproducible path to trustworthy and pedagogy-aligned LLMs for high-stakes educational evaluation.
- OraPO: Oracle-educated Reinforcement Learning for Data-efficient and Factual Radiology Report Generation3
Together, OraPO and FactS create a compact and powerful framework that significantly improves learning efficiency on clinically challenging cases, setting the new SOTA performance on the CheXpert Plus dataset with 2--3 orders of magnitude less training data using a small base VLM on modest hardware.
- A Machine Learning-Optimized Robot-Assisted Driving System for Efficient Flexible Forming of Composite Curved Components3
This study develops a rapid, efficient, and highly precise flexible multi-point forming method for composite components, demonstrating strong potential for industrial applications.
- Towards Event Extraction from Speech with Contextual Clues3
This paper introduces the Speech Event Extraction task and introduces a sequence-to-structure generation paradigm that can produce events from speech signals in an end-to-end manner, together with a conditioned generation method that utilizes speech recognition transcripts as the contextual clue.
- 3
- Improving Machine Reading Comprehension through A Simple Masked-Training Scheme3
A simple yet effective method to improve the EQA performance, termed the [Mask] -for-Answering method (M4A), which is able to produce robust embeddings for both original and masked samples and infer correct answers even with masked context.
- 3
- 3
- 3
- Multi-level, multi-modal interactions for visual question answering over text in images3
A Multi-level Complete Interaction model for the TextVQA task is constructed via stacking multiple blocks composed of the proposed interaction modules, which design a multi-level feature joint prediction approach to exploit output representations from each block in a complementary way to predict answers.
- 3
- Using Knowledge Graphs to Explain Entity Co-occurrence in Twitter3
This paper trains a ranking model using a number of lexical, graph-embedding and popularity-based features over semantic paths containing a single intermediate entity and demonstrates the efficacy of the model for determining why pairs of entities occur together in tweets.
- How Can Reasoner Performance of ABox Intensive Ontologies Be Predicted?3
This paper proposes to improve the representativeness of ontology metrics by developing new metrics which focus on the ABox features of ontologies, and shows that the proposed metrics contribute to overall prediction accuracy for all ontologies in general without causing side-effects.
- Context-driven Concept Search across Web Ontologies using Keyword Queries3
The three key components of the approach are a context for each concept extracted from relevant properties and axioms, query interpretation based on the extracted context and result ranking using learning to rank algorithms.
- 3
- A Meta-reasoner to Rule Them All: Automated Selection of OWL Reasoners Based on Efficiency3
The preliminary evaluation shows that the meta-reasoner significantly and consistently outperforms 6 state-of-the-art reasoners and it achieves a performance close to the hypothetical gold standard reasoner.
- Towards a semantic & domain-agnostic scientific data management system3
PODD is presented, an ontology-centric data management system architecture for scientic experimental data that is extensible and domain independent, and is amenable to greater data reuse and interoperability.
- 3
- An Integrated Formal Approach to Semantic Work Environments Design3
This chapter discusses Semantic Work Environment applications, which use Semantic Web techniques to support the work of the user by collecting knowledge about the current needs in a specific activity, and providing both inferred and augmented knowledge that can then be integrated into current work.
- Validating Semistructured Data Using OWL3
A methodology of encoding the semantics of ORA-SS in the Web Ontology Language (OWL) and automatically validating the semistructured data design using the OWL reasoning tool – RACER is presented.
- Verifying OWL and ORL Ontologies in PVS3
This paper proposes to model OWL and ORL language semantics in PVS specification language so that OWL or ORL ontologies can be transformed and verified in the Prototype Verification System (PVS).
- Demonstration of Schedule and Latency Control in S-MAC3
This demonstration will examine schedule and latency control in S-MAC with Berkeley Motes and demonstrate how specically controlled sleep schedules aect latency and the latency in data transmission in a multi-hop network.
- 2
- Integrating spatial cognition and SLAM for improved performance of autonomous material handling robots in dynamic stockyard environments2
An innovative perception system that combines advanced SLAM-based spatial cognition akin to that of the brain with practical deployment considerations is presented, providing a novel solution for enhancing the operational efficiency and adaptability of autonomous robots in stockyards and similar settings.
- 2
- 2
- 2
- 2
- Teaching Neural Module Networks to Do Arithmetic2
This work upgrades Neural Module Networks by bridging the gap between its interpreter and the complex questions and introducing addition and subtraction modules that perform numerical reasoning over numbers.
- Towards Balanced Defect Prediction with Better Information Propagation2
DPCAG dynamically adjusts the contributions of each node and selects high-confidence nodes for data augmentation and achieves substantial performance superiority when measured by Matthews Correlation Coefficient (MCC), a metric that is widely acknowledged to be the most suitable for imbalanced data.
- 2
- 2
- Vocabulary Matters: A Simple yet Effective Approach to Paragraph-level Question Generation2
A basic sequence-to-sequence QG model is augmented with dynamic, paragraph-specific dictionary and copy attention that is persistent across the corpus, without requiring features generated by sophisticated NLP pipelines or handcrafted rules.
- A General-purpose Visual Query Language for Knowledge Graphs with Bidirectional Transformations.2
The syntax and semantics of GPVQL are presented, the design rationale behind this interactive visual query language is discussed, and the evaluation demonstrates the GPVQL’s superiority in effectiveness and accurateness.
- 2
- Understanding Unnatural Questions Improves Reasoning over Text2
This paper addresses the challenge of learning a high-quality programmer (parser) by projecting natural human-generated questions into unnatural machine-generated Questions which are more convenient to parse by learning a semantic parser that associates synthetic questions with their corresponding action sequences.
- Towards Meta-Reasoning for Ontologies: A Roadmap2
Recent advances in meta-reasoning for Semantic Web ontologies are high-light, technical innovations and results are presented, and important problems for future research are discussed.
- 2
- FFD-Index: An Efficient Indexing Scheme for Star Subgraph Matching on Large RDF Graphs2
This paper presents a novel method to encode a star-shaped subgraph into a bit string and an indexing mechanism to improve the query answering performance, called FFD-index, which significantly outperform the state-of-the-art SPARQL query engine RDF-3X.
- 2
- Extended abstract: towards verifying semistructured data2
This work states that there is no widely accepted formalism that is generally accepted to reason about the properties of the algorithms in semistructured data, and that such a formalism must capture all the necessary semantics required to model the algorithms, should not be too complex, and should be easy to use.
- Reasoning About ORA-SS Data Models Using the Semantic Web2
This paper presents a methodology of encoding the semantics of the ORA-SS notation into the Web Ontology Language (OWL) and automatically verifying the semistructured data design using the OWL reasoning tools.
- RDF FRAMEWORK INSTITUTIONS2
This paper defines the RDF framework in terms of institution theory and investigates the exactness property, which is based on semantically marking up Web resources using ontologies.
- One Model, Two Minds: Task-Conditioned Reasoning for Unified Image Quality and Aesthetic Assessment1
TATAR (Task-Aware Thinking with Asymmetric Rewards), a unified framework that shares the visual-language backbone while conditioning post-training on each task's nature, is proposed and establishes task-conditioned post-training as a principled paradigm for unified perceptual scoring.
- 1
- 1
- Mind Your Margin and Boundary: Are Your Distilled Datasets Truly Robust?1
This work presents Contrastive Curriculum for Robust Dataset Distillation (C$2$R), a framework that couples an attack-aware curriculum with a contrastive robustness objective, and derives a perturbation score that approximates each sample's robust hinge, enabling a curriculum that prioritizes the smallest-margin adversaries that most directly drive robust error.
- Taming the Real-world Complexities in CPT E/M Coding with Large Language Models1
ProFees, the LLM-based framework that tackles E/M encoding automation complexities, achieves an increase in coding accuracy of more than 36% over a commercial CPT E/M coding system and almost 5% over the authors' strongest single-prompt baseline, demonstrating its effectiveness in addressing the real-world complexities.
- 1
- 1
- 1
- 1
- From Planning Stage To FAIR Data: A Practical Metadatasheet For Biomedical Scientists1
This study developed Metadatasheet, a metadata standard based on interviews with members of two biomedical consortia and systematic screening of data repositories that aligns with the data-lifecycle allowing synchronous metadata recording within Microsoft Excel, a widespread data recording software.
- 1
- Double Mixture: Towards Continual Event Detection from Speech1
This paper introduces a new task, continual event detection from speech, and proposes a novel method, 'Double Mixture,' which merges speech expertise with robust memory mechanisms to enhance adaptability and prevent forgetting.
- 1
- Key factors influencing Retail Store Expansion Decisions: Case study of combining evidence- and data- driven approach1
A list of factors that need to be considered to support retail store expansion decisions is established and insights drawn from 10 years of operational data are drilled down on the key factors that influence the decision-making process.
- 1
- 1
- Sip4J: Statically inferring permission-based specifications for sequential Java programs.1
This paper presents a framework, Sip4J, to automatically extract implicit dependencies from sequential Java programs in the form of access permissions, by performing inter-procedural static analysis of the source code and gives strong evidence of the correctness of the inferred annotations and their effectiveness in enabling concurrency in sequential programs.
- MDS-based Visual Survey of Biological Data Visualization Techniques1
A large number of novel methods and tools for biological data visualization have been developed and published in the past 15 years, and more are expected to be developed this year.
- 1
- 1
- 1
- 1
- Enriching concept search across semantic web ontologies1
A novel approach of indexing concepts using ontology axioms in an inverted file structure and ranking them using a dynamic ranking algorithm is proposed, outperforming the search function of BioPortal, a large and widely-used ontology repository.
- 1
- The SKELETOME Project: Towards a community-driven knowledge curation platform for Skeletal Dysplasias1
In parallel, several systems enabling case studies management and fostering knowledge exchange between domain experts have been developed (e.g., ESDN), but their functionalities rise only to the level of a discussion forum and lack any real support for advanced features.
- MIMO interference alignment for cognitive radio network1
This paper designs an ICA CU system as a 2 × 2 MIMO OFDM system, and uses inverse matrix to cancel the PU signal interference, which is not limited in the case that a MIMo-OFDM system of cognitive users in a wide spectrum range, and the primary user operates at a narrower channel bandwidth in overlap with the channel of the cognitive user.
- Scale-Out RDF Molecule Store for Efficient, Scalable Data Integration and Querying1
Resource Description Framework (RDF) and Web Ontology Language (OWL) offer significant potential as technologies designed to support the integration of and reasoning across heterogeneous disparate data sources.
- 1
- Research into Verifying Semistructured Data1
This paper modelled the semantics expressed in the ORA-SS (Object Relationship Attribute data model for SemiStructured data) data modelling notation in two formal languages that have automatic verification tools.
- TCOZ approach to semantic web services design1
An integrated formal modeling language, Timed Communicating Object Z, is applied to design SW services and the development of the systematic translation rules and tools which can automatically extract the SW ontology and services semantic markup from the formal TCOZ design model are presented.
- Enhancing LLM Medical Coding with Structured External Knowledge–
RAG-Coding is introduced, an agentic, training-free method that augments LLMs with structured external knowledge: the tabular list is encoded as a knowledge graph capturing hierarchical and instructional code relationships, and the guidelines are distilled into concise, code-specific summaries rather than retrieved as raw text.
- –
- Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matching–
FlowSG recasts SGG as continuous-time transport on a hybrid discrete-continuous state, which validates the mixed discrete-continuous generative formulation over one-shot classification baselines, and shows consistent gains in predicate R/mR and graph-level metrics.
- –
- Scalable and effective negative sample generation for hyperedge prediction–
This work introduces SEHP (Scalable and Effective Negative Sample Generation for Hyperedge Prediction), which employs a conditional diffusion model to iteratively generate and refine negative hyperedges, thereby advancing them towards the decision boundary to improve model performance.
- –
- –
- –
- –
- –
- –
- –
- –
- Dataset | Mindset = Explainable AI | Interpretable AI–
It is argued that XAI is a subset of IAI, and the demarcation of XAI and IAI is indispensable because it would be impossible to determine regulatory policies for many AI applications, especially in healthcare, human resources, banking, and finance.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Kinematics Analysis of a Mobile 6-DOF Coal Sampling Robot–
This paper first introduced the mechanical structure of the 6-DOF sampling robot, then the forward kinematics equation of the sampling robot was established by the DH method, and the interference situation of the sampled robot with coal containers in the sampling process was analyzed, and whether the interference exists or not was given.
- Dynamic Characteristics Analysis of the Hydraulic Arm of Mobile Coal Sampling Robot–
The hydraulic arm of the MCYY2000 mobile coal sampling robot is taken as the research object, and a simplified model of the hydraulic arm is established with SolidWorks to obtain the joint torques and hydraulic driving forces of the Hydraulic arm under different conditions.
- –
- Semantic Technology–
This paper proposes to improve the representativeness of ontology metrics by developing new metrics which focus on the ABox features of ontologies, and shows that the proposed metrics contribute to overall prediction accuracy for all ontologies in general without causing side-effects.
- VAStream: Virtual adaptive substream partition and scheduling in data-driven P2P live streaming–
This paper proposes a virtual adaptive substream partition and scheduling protocol, namely VAStream, which can enforce substREAM partition or merge operation based on the current P2P network status and presents properly crafted schemes to deal with the issues in complex network situation.
- An Adaptive Scheduling Algorithm for Real-Time Business over Bluetooth Sensor Networks–
The simulation results indicate that this adaptive scheduling algorithm for real-time business over Bluetooth sensor networks has better bandwidth utilization, higher fairness and lower scheduling delay than traditional scheduling algorithms.
- –
- –
- –
- –
- –
- Towards Verifying Semistructured Data–
The semantics that are required to reason about the properties of algorithms are determined, they are modelled using two different logics and automatic verification is used to reasonAbout the properties.
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.